Human Control Performance in Solving Multi-UAV Dynamic Vehicle Routing Problems Using an Ecological Interface

Abstract
Real-time optimization of Vehicle Routing Problems during mission operations raises concerns regarding reliability of obtaining a solution and solution time. Improvements in control performance by having a human-in-the-loop might be possible by leveraging human visual pattern recognition qualities. By developing an ecological interface, supporting the operator in controlling multiple Unmanned Aerial Vehicles in a simulated payload delivery mission, and by conducting a human-in-the-loop experiment, interface effectiveness and human control performance in Dynamic Vehicle Routing Problems was investigated. Results show the ecological interface offers good support and scales well with problem size. Results also show participants can in some cases achieve solutions faster and more reliably compared to an optimization algorithm, although generally yielding less efficient solutions. Having a human-in-the-loop can thus offer improved control performance over relying on pure automation, especially in time critical situations.